arXiv subjects

Yifan Chen

Publications and source records attributed to Yifan Chen.

At least 127 records · Page 7Linked to original sources

arXiv2025

On Kähler-Einstein Currents

We show that a general class of singular Kähler metrics with Ricci curvature bounded below define Kähler currents. In particular the result applies to singular Kähler-Einstein metrics on klt pairs, and an analogous result holds for Kähler-Ricci solitons. In addition we show that if a singular Kähler-Einstein metric can be approximated by smooth metrics on a resolution whose Ricci curvature has negative part that is bounded uniformly in $L^p$ for $p > \frac{2n-1}{n}$, then the metric defines an RCD space.

math.DG↗

arXiv2025

Mori dream spaces and Q-homology quadrics

We show that Shavel type surfaces are fake quadrics of even type which are not Mori dream surfaces, yet there are infinitely many primes $p$ such that the reduction modulo $p$ is a Mori dream surface. We investigate fake quadrics, first concerning the property of being Mori dream surfaces, then we try to determine which surfaces isogenous to a product are fake quadrics of even type.

math.AG↗

arXiv2025

Cavity as Radio Telescope for Galactic Dark Photon

Dark photons, as a minimal extension of the Standard Model through an additional Abelian gauge group, may propagate relativistically across the galaxy, originating from dark matter decay or annihilation, thereby contributing to a galactic dark photon background. The generation of dark photons typically favors certain polarization modes, which are dependent on the interactions between dark matter and dark photons. We introduce a framework in which a resonant cavity is utilized to detect and differentiate these polarizations, leveraging the daily variation in expected signals due to the anisotropic distribution of dark photons and the rotation of the Earth. We conduct an experimental search using superconducting radio-frequency cavities, noted for their exceptionally high quality factors, proving them to be effective telescopes for observing galactic dark photons. This approach establishes the most stringent limits yet on the kinetic mixing coefficient between dark photons and electromagnetic photons, thereby unveiling a novel avenue for the indirect search for dark matter via multi-messenger astronomy.

hep-ph↗

arXiv2025

Catch Causal Signals from Edges for Label Imbalance in Graph Classification

Despite significant advancements in causal research on graphs and its application to cracking label imbalance, the role of edge features in detecting the causal effects within graphs has been largely overlooked, leaving existing methods with untapped potential for further performance gains. In this paper, we enhance the causal attention mechanism through effectively leveraging edge information to disentangle the causal subgraph from the original graph, as well as further utilizing edge features to reshape graph representations. Capturing more comprehensive causal signals, our design leads to improved performance on graph classification tasks with label imbalance issues. We evaluate our approach on real-word datasets PTC, Tox21, and ogbg-molhiv, observing improvements over baselines. Overall, we highlight the importance of edge features in graph causal detection and provide a promising direction for addressing label imbalance challenges in graph-level tasks. The model implementation details and the codes are available on https://github.com/fengrui-z/ECAL

cs.LG↗

arXiv2025

MLP Fusion: Towards Efficient Fine-tuning of Dense and Mixture-of-Experts Language Models

Fine-tuning a pre-trained language model (PLM) emerges as the predominant strategy in many natural language processing applications. However, this process is known to be expensive, especially on edge devices with low computing power. While general approaches (e.g. quantization and distillation) have been widely studied to reduce the compute/memory of PLM fine-tuning, one-shot compression techniques specifically designed for fine-tuning remain largely unexplored. In this paper, we investigate the neural tangent kernel (NTK)--which reveals the gradient descent dynamics of neural networks--of the multilayer perceptrons (MLP) modules in a PLM and propose to coin a lightweight PLM through NTK-approximating MLP fusion. By incorporating NTK into the compression process, MLP Fusion not only preserves the original model's output but also maintains its training dynamics. To achieve this, we reconsider the MLP as a bundle of sub-MLPs and cluster them into a given number of centroids, which can then be restored as a compressed MLP and surprisingly well approximate the NTK of the original PLM. Our approach is applicable to both standard MLP modules and Mixture-of-Experts (MoE) modules in PLMs, demonstrating its scalability and versatility. Additionally, we provide theoretical derivations to demonstrate how the proposed compression preserves the NTK. Extensive experiments of PLM fine-tuning on both natural language understanding and generation tasks are provided to verify the effectiveness of MLP fusion. Our code is available at https://github.com/weitianxin/MLP_Fusion.

cs.LG↗

arXiv2025

LeetDecoding: A PyTorch Library for Exponentially Decaying Causal Linear Attention with CUDA Implementations

The machine learning and data science community has made significant while dispersive progress in accelerating transformer-based large language models (LLMs), and one promising approach is to replace the original causal attention in a generative pre-trained transformer (GPT) with \emph{exponentially decaying causal linear attention}. In this paper, we present LeetDecoding, which is the first Python package that provides a large set of computation routines for this fundamental operator. The launch of LeetDecoding was motivated by the current lack of (1) clear understanding of the complexity regarding this operator, (2) a comprehensive collection of existing computation methods (usually spread in seemingly unrelated fields), and (3) CUDA implementations for fast inference on GPU. LeetDecoding's design is easy to integrate with existing linear-attention LLMs, and allows for researchers to benchmark and evaluate new computation methods for exponentially decaying causal linear attention. The usage of LeetDecoding does not require any knowledge of GPU programming and the underlying complexity analysis, intentionally making LeetDecoding accessible to LLM practitioners. The source code of LeetDecoding is provided at \href{https://github.com/Computational-Machine-Intelligence/LeetDecoding}{this GitHub repository}, and users can simply install LeetDecoding by the command \texttt{pip install leet-decoding}.

cs.LG↗

arXiv2025

Remodeling Peptide-MHC-TCR Triad Binding as Sequence Fusion for Immunogenicity Prediction

The complex nature of tripartite peptide-MHC-TCR interactions is a critical yet underexplored area in immunogenicity prediction. Traditional studies on TCR-antigen binding have not fully addressed the complex dependencies in triad binding. In this paper, we propose new modeling approaches for these tripartite interactions, utilizing sequence information from MHCs, peptides, and TCRs. Our methods adhere to native sequence forms and align with biological processes to enhance prediction accuracy. By incorporating representation learning techniques, we introduce a fusion mechanism to integrate the three sequences effectively. Empirical experiments show that our models outperform traditional methods, achieving a 2.8 to 13.3 percent improvement in prediction accuracy across existing benchmarks. We further validate our approach with extensive ablation studies, demonstrating the effectiveness of the proposed model components. The model implementation, code, and supplementary materials, including a manuscript with colored hyperlinks and a technical appendix for digital viewing, will be open-sourced upon publication.

q-bio.BM↗

arXiv2024

Optimized Gradient Clipping for Noisy Label Learning

Previous research has shown that constraining the gradient of loss function with respect to model-predicted probabilities can enhance the model robustness against noisy labels. These methods typically specify a fixed optimal threshold for gradient clipping through validation data to obtain the desired robustness against noise. However, this common practice overlooks the dynamic distribution of gradients from both clean and noisy-labeled samples at different stages of training, significantly limiting the model capability to adapt to the variable nature of gradients throughout the training process. To address this issue, we propose a simple yet effective approach called Optimized Gradient Clipping (OGC), which dynamically adjusts the clipping threshold based on the ratio of noise gradients to clean gradients after clipping, estimated by modeling the distributions of clean and noisy samples. This approach allows us to modify the clipping threshold at each training step, effectively controlling the influence of noise gradients. Additionally, we provide statistical analysis to certify the noise-tolerance ability of OGC. Our extensive experiments across various types of label noise, including symmetric, asymmetric, instance-dependent, and real-world noise, demonstrate the effectiveness of our approach.

cs.LG↗

arXiv2024

Stochastic Frequency Fluctuation Super-Resolution Imaging

The inherent non-linearity of intensity correlation functions can be used to spatially distinguish identical emitters beyond the diffraction limit, as achieved, for example, in Super-Resolution Optical Fluctuation Imaging (SOFI). Here, we propose a complementary concept based on spectral correlation functions, termed Spectral Fluctuation Super-Resolution (SFSR) imaging. Through theoretical and computational analysis, we show that spatially resolving time-frequency correlation functions in the image plane can improve the imaging resolution by a factor of $\sqrt2$ in most cases and up to twofold for strictly two emitters. This improvement is achieved by quantifying the degree of correlation in spectral fluctuations across the spatial domain. Experimentally, SFSR can be implemented using a combination of interferometry and photon-correlation measurements. The method works for non-blinking emitters and stochastic spectral fluctuations with arbitrary temporal statistics. This suggests its utility in super-resolution microscopy of quantum emitters at low temperatures, where spectral diffusion is often more pronounced than emitter blinking.

physics.optics↗

arXiv2024

On Motivic Zeta Functions and Stringy E-function via Embedded $\mathbb{Q}$-Resolution

We provide the formula of motivic zeta function for semi-quasihomogeneous singularities and in dimension two, we determine the poles of zeta functions. We also give another formula for stringy E-function using embedded $\mathbb{Q}$-resolution, and we utilize it to calculate the stringy E-function for semi-quasihomogeneous polynomials and non-degenerate polynomials.

math.AG↗

arXiv2024

Searches for exotic spin-dependent interactions with spin sensors

Numerous theories have postulated the existence of exotic spin-dependent interactions beyond the Standard Model of particle physics. Spin-based quantum sensors, which utilize the quantum properties of spins to enhance measurement precision, emerge as powerful tools for probing these exotic interactions. These sensors encompass a wide range of technologies, such as optically pumped magnetometers, atomic comagnetometers, spin masers, nuclear magnetic resonance, spin amplifiers, and nitrogen-vacancy centers. These technologies stand out for their ultrahigh sensitivity, compact tabletop design, and cost-effectiveness, offering complementary approaches to the large-scale particle colliders and astrophysical observations. This article reviews the underlying physical principles of various spin sensors and highlights the recent theoretical and experimental progress in the searches for exotic spin-dependent interactions with these quantum sensors. Investigations covered include the exotic interactions of spins with ultralight dark matter, exotic spin-dependent forces, electric dipole moment, spin-gravity interactions, and among others. Ongoing and forthcoming experiments using advanced spin-based sensors to investigate exotic spin-dependent interactions are discussed.

quant-ph↗

arXiv2024

Revisiting Energy-Based Model for Out-of-Distribution Detection

Out-of-distribution (OOD) detection is an essential approach to robustifying deep learning models, enabling them to identify inputs that fall outside of their trained distribution. Existing OOD detection methods usually depend on crafted data, such as specific outlier datasets or elaborate data augmentations. While this is reasonable, the frequent mismatch between crafted data and OOD data limits model robustness and generalizability. In response to this issue, we introduce Outlier Exposure by Simple Transformations (OEST), a framework that enhances OOD detection by leveraging "peripheral-distribution" (PD) data. Specifically, PD data are samples generated through simple data transformations, thus providing an efficient alternative to manually curated outliers. We adopt energy-based models (EBMs) to study PD data. We recognize the "energy barrier" in OOD detection, which characterizes the energy difference between in-distribution (ID) and OOD samples and eases detection. PD data are introduced to establish the energy barrier during training. Furthermore, this energy barrier concept motivates a theoretically grounded energy-barrier loss to replace the classical energy-bounded loss, leading to an improved paradigm, OEST*, which achieves a more effective and theoretically sound separation between ID and OOD samples. We perform empirical validation of our proposal, and extensive experiments across various benchmarks demonstrate that OEST* achieves better or similar accuracy compared with state-of-the-art methods.

cs.CV↗

arXiv2024

Theseus: Exploring Efficient Wafer-Scale Chip Design for Large Language Models

The emergence of the large language model~(LLM) poses an exponential growth of demand for computation throughput, memory capacity, and communication bandwidth. Such a demand growth has significantly surpassed the improvement of corresponding chip designs. With the advancement of fabrication and integration technologies, designers have been developing Wafer-Scale Chips~(WSCs) to scale up and exploit the limits of computation density, memory capacity, and communication bandwidth at the level of a single chip. Existing solutions have demonstrated the significant advantages of WSCs over traditional designs, showing potential to effectively support LLM workloads. Despite the benefits, exploring the early-stage design space of WSCs for LLMs is a crucial yet challenging task due to the enormous and complicated design space, time-consuming evaluation methods, and inefficient exploration strategies. To address these challenges, we propose Theseus, an efficient WSC design space exploration framework for LLMs. We construct the design space of WSCs with various constraints considering the unique characteristics of WSCs. We propose efficient evaluation methodologies for large-scale NoC-based WSCs and introduce multi-fidelity Bayesian optimization to efficiently explore the design space. Evaluation results demonstrate the efficiency of Theseus that the searched Pareto optimal results outperform GPU cluster and existing WSC designs by up to 62.8\%/73.7\% in performance and 38.6\%/42.4\% in power consumption for LLM training, while improving up to 23.2$\times$ and 15.7$\times$ for the performance and power of inference tasks. Furthermore, we conduct case studies to address the design tradeoffs in WSCs and provide insights to facilitate WSC designs for LLMs.

cs.AR↗

arXiv2024

LayoutDiT: Exploring Content-Graphic Balance in Layout Generation with Diffusion Transformer

Layout generation is a foundation task of graphic design, which requires the integration of visual aesthetics and harmonious expression of content delivery. However, existing methods still face challenges in generating precise and visually appealing layouts, including blocking, overlapping, small-sized, or spatial misalignment. We found that these methods overlook the crucial balance between learning content-aware and graphic-aware features. This oversight results in their limited ability to model the graphic structure of layouts and generate reasonable layout arrangements. To address these challenges, we introduce LayoutDiT, an effective framework that balances content and graphic features to generate high-quality, visually appealing layouts. Specifically, we first design an adaptive factor that optimizes the model's awareness of the layout generation space, balancing the model's performance in both content and graphic aspects. Secondly, we introduce a graphic condition, the saliency bounding box, to bridge the modality difference between images in the visual domain and layouts in the geometric parameter domain. In addition, we adapt a diffusion transformer model as the backbone, whose powerful generative capability ensures the quality of layout generation. Benefiting from the properties of diffusion models, our method excels in constrained settings without introducing additional constraint modules. Extensive experimental results demonstrate that our method achieves superior performance in both constrained and unconstrained settings, significantly outperforming existing methods.

cs.CV↗

arXiv2024

When Spatial meets Temporal in Action Recognition

Video action recognition has made significant strides, but challenges remain in effectively using both spatial and temporal information. While existing methods often focus on either spatial features (e.g., object appearance) or temporal dynamics (e.g., motion), they rarely address the need for a comprehensive integration of both. Capturing the rich temporal evolution of video frames, while preserving their spatial details, is crucial for improving accuracy. In this paper, we introduce the Temporal Integration and Motion Enhancement (TIME) layer, a novel preprocessing technique designed to incorporate temporal information. The TIME layer generates new video frames by rearranging the original sequence, preserving temporal order while embedding $N^2$ temporally evolving frames into a single spatial grid of size $N \times N$. This transformation creates new frames that balance both spatial and temporal information, making them compatible with existing video models. When $N=1$, the layer captures rich spatial details, similar to existing methods. As $N$ increases ($N\geq2$), temporal information becomes more prominent, while the spatial information decreases to ensure compatibility with model inputs. We demonstrate the effectiveness of the TIME layer by integrating it into popular action recognition models, such as ResNet-50, Vision Transformer, and Video Masked Autoencoders, for both RGB and depth video data. Our experiments show that the TIME layer enhances recognition accuracy, offering valuable insights for video processing tasks.

cs.CV↗

arXiv2024

Principled Probabilistic Imaging using Diffusion Models as Plug-and-Play Priors

Diffusion models (DMs) have recently shown outstanding capabilities in modeling complex image distributions, making them expressive image priors for solving Bayesian inverse problems. However, most existing DM-based methods rely on approximations in the generative process to be generic to different inverse problems, leading to inaccurate sample distributions that deviate from the target posterior defined within the Bayesian framework. To harness the generative power of DMs while avoiding such approximations, we propose a Markov chain Monte Carlo algorithm that performs posterior sampling for general inverse problems by reducing it to sampling the posterior of a Gaussian denoising problem. Crucially, we leverage a general DM formulation as a unified interface that allows for rigorously solving the denoising problem with a range of state-of-the-art DMs. We demonstrate the effectiveness of the proposed method on six inverse problems (three linear and three nonlinear), including a real-world black hole imaging problem. Experimental results indicate that our proposed method offers more accurate reconstructions and posterior estimation compared to existing DM-based imaging inverse methods.

eess.IV↗

arXiv2024

Einstein Probe discovery of EP240408a: a peculiar X-ray transient with an intermediate timescale

We report the discovery of a peculiar X-ray transient, EP240408a, by Einstein Probe (EP) and follow-up studies made with EP, Swift, NICER, GROND, ATCA and other ground-based multi-wavelength telescopes. The new transient was first detected with Wide-field X-ray Telescope (WXT) on board EP on April 8th, 2024, manifested in an intense yet brief X-ray flare lasting for 12 seconds. The flare reached a peak flux of 3.9x10^(-9) erg/cm2/s in 0.5-4 keV, about 300 times brighter than the underlying X-ray emission detected throughout the observation. Rapid and more precise follow-up observations by EP/FXT, Swift and NICER confirmed the finding of this new transient. Its X-ray spectrum is non-thermal in 0.5-10 keV, with a power-law photon index varying within 1.8-2.5. The X-ray light curve shows a plateau lasting for about 4 days, followed by a steep decay till becoming undetectable about 10 days after the initial detection. Based on its temporal property and constraints from previous EP observations, an unusual timescale in the range of 7-23 days is found for EP240408a, which is intermediate between the commonly found fast and long-term transients. No counterparts have been found in optical and near-infrared, with the earliest observation at 17 hours after the initial X-ray detection, suggestive of intrinsically weak emission in these bands. We demonstrate that the remarkable properties of EP240408a are inconsistent with any of the transient types known so far, by comparison with, in particular, jetted tidal disruption events, gamma-ray bursts, X-ray binaries and fast blue optical transients. The nature of EP240408a thus remains an enigma. We suggest that EP240408a may represent a new type of transients with intermediate timescales of the order of about 10 days. The detection and follow-ups of more of such objects are essential for revealing their origin.

astro-ph.HE↗

arXiv2024

Randomly pivoted Cholesky: Practical approximation of a kernel matrix with few entry evaluations

The randomly pivoted partial Cholesky algorithm (RPCholesky) computes a factorized rank-k approximation of an N x N positive-semidefinite (psd) matrix. RPCholesky requires only (k + 1) N entry evaluations and O(k^2 N) additional arithmetic operations, and it can be implemented with just a few lines of code. The method is particularly useful for approximating a kernel matrix. This paper offers a thorough new investigation of the empirical and theoretical behavior of this fundamental algorithm. For matrix approximation problems that arise in scientific machine learning, experiments show that RPCholesky matches or beats the performance of alternative algorithms. Moreover, RPCholesky provably returns low-rank approximations that are nearly optimal. The simplicity, effectiveness, and robustness of RPCholesky strongly support its use in scientific computing and machine learning applications.

math.NA↗